© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16188
    Prev
    Next
    INDEX
    Explanations

    code snippets and series of numbers, particularly in a structured data format

    oai_token-act-pair · gemini-2.0-flash

    numerical/code sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.46
     سكانية
    -0.44
    FunctionFlags
    -0.43
    كتشاف
    -0.40
    nonumber
    -0.39
     katalog
    -0.39
    elin
    -0.39
     Am
    -0.37
    atkan
    -0.37
     centri
    -0.36
    POSITIVE LOGITS
     للاسماء
    0.88
    aarrggbb
    0.80
     الحره
    0.75
    ScopeManager
    0.73
    </tfoot>
    0.72
    NavController
    0.68
     InputDecoration
    0.68
    SceneManagement
    0.66
    ibouti
    0.64
    الإنجليزية
    0.63
    Activations Density 5.762%

    No Known Activations